Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 60564
    Prev
    Next
    INDEX
    Explanations

    Middle East

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     multiprocessing
    -0.08
    -0.08
     Antoine
    -0.08
     perpendicular
    -0.08
    Spect
    -0.08
    ไม้
    -0.08
     poisson
    -0.08
     recol
    -0.08
    Andy
    -0.07
    spect
    -0.07
    POSITIVE LOGITS
     milieu
    0.08
     عرب
    0.08
     abode
    0.08
    /AIDS
    0.08
     desal
    0.08
     Affairs
    0.08
     привет
    0.08
     മേഖ
    0.08
     മേഖല
    0.07
     Saudi
    0.07
    Activations Density 0.005%

    No Known Activations